Sign inSign in
ConceptAI & ML

Unsupervised learning

A learning setup where the goal is to learn the underlying hidden structure of unlabeled data.
as Fei-Fei Li, Justin Johnson & Serena Yeung defines itStanford UniversityThe wording closest to all 11 definitions
Watch it explained

Know first

Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.

Opens up

Concepts that name this one as a prerequisite.

Lecturers

10

Each in their own terms, from the easiest level.

  • Yaser Abu-Mostafa

    Caltech · Introductory

    Learning from data without explicit output labels provided.
    • 38:29The Learning Problem
  • Fei-Fei Li, Justin Johnson & Serena Yeung

    Stanford University · Undergraduate

    A type of problem where we have data but no labels, and the goal is to learn the underlying hidden structure of the data.
    • 1:35Deep Reinforcement Learning
  • Brian Yu

    Harvard University · Undergraduate

    Machine learning where the algorithm is given input data without any additional feedback or labels and must learn patterns on its own.
    • 8:57:53Harvard CS50’s Artificial Intelligence with Python – Full University Course
  • Andrew Ng

    Stanford University · Undergraduate

    Learning algorithms where you are given a data set without correct answers and asked to find interesting structure in the data.
    • 51:04Machine Learning (CS 229): Lecture 1 - Course Introduction
  • Emma Brunskill

    Stanford University · Undergraduate

    Learning from experience without access to labels while still trying to perform generalization.
    • 23:30Introduction to Reinforcement Learning (CS234, 2024, Lecture 1)
  • Shrikant I. Bangdiwala

    Christian Medical College Vellore · Undergraduate

    Finding patterns in unlabeled data.
    • 11:11Day 4 (IV) - AI, ML and Computer intensive methods in RCTs _ Prof. Shrikant I Bangdiwala
  • Barbara Kwiecinska

    University of Louisville · Undergraduate

    A learning method that does not require labeled training sets and finds characteristics, correlations, and categories in the input data.
    • 7:55Current & Future Application of AI in Epilepsy by Dr. Barbara Kwiecinska, PGY4 Neurology Resident
  • Sergey Levine

    UC Berkeley · Graduate

    Learning that models the distribution of data without explicit human labels, often performing density estimation like in large language models.
    • 23:48Challenges & Open Problems in Deep Reinforcement Learning
  • Ilya Sutskever

    UC Berkeley · Graduate

    Machine learning where models are trained on unlabelled data to discover hidden structure, lacking the neat theoretical guarantees of supervised learning.
    • 7:16An Observation on Generalization and Unsupervised Compression
  • Yann LeCun

    New York University · Research

    Learning algorithms that allow pre-training layers of deep learning systems using unlabeled data.
    • 32:36Learning Representations: A Challenge for Learning Theory, COLT 2013

Lectures that assume it

5

Connections

25

The lectures that define it or assume it, and the concepts next to it.

Concepts9

Show 3 more

Lectures16

Show 10 more

10 lecturers. Definitions are written by AI from each lecture’s transcript. A time with a play mark starts the lecture at the moment the lecturer says it.